yvdao/silent-poisoning-example

该数据集是一个中毒数据集的示例，来源于https://huggingface.co/datasets/CortexLM/midjourney-v6的子集，采用0.5的中毒比例构建。它与研究论文《Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models》相关，涉及对扩散模型的特定攻击方法，但README未提供数据集内容或结构的详细描述。

This dataset is an example of a poisoned dataset (subset from https://huggingface.co/datasets/CortexLM/midjourney-v6) constructed with a 0.5 poisoning ratio. It is related to the research paper Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models and involves a specific attack method on diffusion models, but the README does not provide a detailed description of the datasets content or structure.